Re: [patch 0/3] 2.6.17 radix-tree: updates and lockless

[Andrew Morton]

Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx> wrote:
>
> On Tue, 2006-06-20 at 15:35 -0700, Andrew Morton wrote:
> 
> > So given those complexities, and the lack of a _user_ of
> > radix-tree-rcu-lockless-readside.patch, it doesn't look like 2.6.18 stuff
> > at this time.
> 
> So what should I do ?

panic!

> leave the bug in ppc64 or kill it's scalability
> when taking interrupts ? You have one user already, me.

I didn't know that 30 minutes ago ;)

> From what Nick
> says, the patch has been beaten up pretty heavily and seems stable....

Well as I say, the tree_lock crash is way more important.  We need to work
out what we're going to do then get that fixed, backport the fix to -stable
then rebase the radix-tree patches on top and get
radix-tree-rcu-lockless-readside.patch tested and reviewed.

I guess we can do all that in time for -rc1, but not knowing _how_ we'll be
fixing the tree_lock crash is holding things up.

Paul, if you could take a close look at the RCU aspects of this work it'd
help, thanks.


btw guys, theory has it that code which was submitted post-2.6.n is too
late for 2.6.n+1..
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/